| { | |
| "best_metric": 0.4777088761329651, | |
| "best_model_checkpoint": "Meta-Llama-3.1-8B-Instruct\\checkpoint-100", | |
| "epoch": 0.3838771593090211, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03838771593090211, | |
| "grad_norm": 0.6985546946525574, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07677543186180422, | |
| "grad_norm": 0.7653126120567322, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11516314779270634, | |
| "grad_norm": 7.446228981018066, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7674, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15355086372360843, | |
| "grad_norm": 0.1999460607767105, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6419, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19193857965451055, | |
| "grad_norm": 0.16155661642551422, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5839, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23032629558541268, | |
| "grad_norm": 0.12439702451229095, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5252, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2687140115163148, | |
| "grad_norm": 0.1331063061952591, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5171, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30710172744721687, | |
| "grad_norm": 0.115571029484272, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5038, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.345489443378119, | |
| "grad_norm": 0.13240906596183777, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4863, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "grad_norm": 0.16940464079380035, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4795, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "eval_loss": 0.4777088761329651, | |
| "eval_runtime": 812.7316, | |
| "eval_samples_per_second": 0.191, | |
| "eval_steps_per_second": 0.025, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 780, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.43125039448064e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |